110 citations · 168 across the 18 of their papers we have counts for
23 papers
Simulation Priors for Data-Efficient Deep Learning
Lenart Treven, Bhavya Sukhija, Jonas Rothfuss +3
How do we enable AI systems to efficiently learn in the real-world? First-principles models are widely used to simulate natural systems, but often fail to capture real-world comple…
SequenceLayers: Sequence Processing and Streaming Neural Networks Made Easy
RJ Skerry-Ryan, Julian Salazar, Soroosh Mariooryad +8
We introduce a neural network layer API and library for sequence modeling, designed for easy creation of sequence models that can be executed both layer-by-layer (e.g., teacher-for…
Bridging the Sim-to-Real Gap with Bayesian Inference
Jonas Rothfuss, Bhavya Sukhija, Lenart Treven +3
We present SIM-FSVGD for learning robot dynamics from data. As opposed to traditional methods, SIM-FSVGD leverages low-fidelity physical priors, e.g., in the form of simulators, to…
Data-Efficient Task Generalization via Probabilistic Model-based Meta Reinforcement Learning
Arjun Bhardwaj, Jonas Rothfuss, Bhavya Sukhija +4
We introduce PACOH-RL, a novel model-based Meta-Reinforcement Learning (Meta-RL) algorithm designed to efficiently adapt control policies to changing dynamics. PACOH-RL meta-learns…
Hallucinated Adversarial Control for Conservative Offline Policy Evaluation
Jonas Rothfuss, Bhavya Sukhija, Tobias Birchler +2
We study the problem of conservative off-policy evaluation (COPE) where given an offline dataset of environment interactions, collected by other agents, we seek to obtain a (tight)…
Scalable PAC-Bayesian Meta-Learning via the PAC-Optimal Hyper-Posterior: From Theory to Practice
Jonas Rothfuss, Martin Josifoski, Vincent Fortuin +1
Meta-Learning aims to speed up the learning process on new tasks by acquiring useful inductive biases from datasets of related learning tasks. While, in practice, the number of rel…
Instance-Dependent Generalization Bounds via Optimal Transport
Songyan Hou, Parnian Kassraie, Anastasis Kratsios +2
Existing generalization bounds fail to explain crucial factors that drive the generalization of modern neural networks. Since such bounds often hold uniformly over all parameters,…
Lifelong Bandit Optimization: No Prior and No Regret
Felix Schur, Parnian Kassraie, Jonas Rothfuss +1
Machine learning algorithms are often repeatedly applied to problems with similar structure over and over again. We focus on solving a sequence of bandit optimization tasks and dev…
MARS: Meta-Learning as Score Matching in the Function Space
Krunoslav Lehman Pavasovic, Jonas Rothfuss, Andreas Krause
Meta-learning aims to extract useful inductive biases from a set of related datasets. In Bayesian meta-learning, this is typically achieved by constructing a prior distribution ove…
Meta-Learning Priors for Safe Bayesian Optimization
Jonas Rothfuss, Christopher Koenig, Alisa Rupenyan +1
In robotics, optimizing controller parameters under safety constraints is an important challenge. Safe Bayesian optimization (BO) quantifies uncertainty in the objective and constr…
BaCaDI: Bayesian Causal Discovery with Unknown Interventions
Alexander Hägele, Jonas Rothfuss, Lars Lorch +3
Inferring causal structures from experimentation is a central task in many domains. For example, in biology, recent advances allow us to obtain single-cell expression data under mu…
Amortized Inference for Causal Structure Learning
Lars Lorch, Scott Sussex, Jonas Rothfuss +2
Inferring causal structure poses a combinatorial search problem that typically involves evaluating structures with a score or independence test. The resulting search is costly, and…
Meta-Learning Hypothesis Spaces for Sequential Decision-making
Parnian Kassraie, Jonas Rothfuss, Andreas Krause
Obtaining reliable, adaptive confidence sets for prediction functions (hypotheses) is a central challenge in sequential decision-making tasks, such as bandits and model-based reinf…
Variational Causal Networks: Approximate Bayesian Inference over Causal Structures
Yashas Annadani, Jonas Rothfuss, Alexandre Lacoste +4
Learning the causal structure that underlies data is a crucial step towards robust real-world decision making. The majority of existing work in causal inference focuses on determin…
Meta-Learning Reliable Priors in the Function Space
Jonas Rothfuss, Dominique Heyn, Jinfan Chen +1
When data are scarce meta-learning can improve a learner's accuracy by harnessing previous experience from related learning tasks. However, existing methods have unreliable uncerta…
DiBS: Differentiable Bayesian Structure Learning
Lars Lorch, Jonas Rothfuss, Bernhard Schölkopf +1
Bayesian structure learning allows inferring Bayesian network structure from data while reasoning about the epistemic uncertainty -- a key element towards enabling active causal di…
Robustness to Pruning Predicts Generalization in Deep Neural Networks
Lorenz Kuhn, Clare Lyle, Aidan N. Gomez +2
Existing generalization measures that aim to capture a model's simplicity based on parameter counts or norms fail to explain generalization in overparameterized deep neural network…
PACOH: Bayes-Optimal Meta-Learning with PAC-Guarantees
Jonas Rothfuss, Vincent Fortuin, Martin Josifoski +1
Meta-learning can successfully acquire useful inductive biases from data. Yet, its generalization properties to unseen learning tasks are poorly understood. Particularly if the num…
Noise Regularization for Conditional Density Estimation
Jonas Rothfuss, Fabio Ferreira, Simon Boehm +4
Modelling statistical relationships beyond the conditional mean is crucial in many settings. Conditional density estimation (CDE) aims to learn the full conditional probability den…
Conditional Density Estimation with Neural Networks: Best Practices and Benchmarks
Jonas Rothfuss, Fabio Ferreira, Simon Walther +1
Given a set of empirical observations, conditional density estimation aims to capture the statistical relationship between a conditional variable and a dependent varia…
ProMP: Proximal Meta-Policy Search
Jonas Rothfuss, Dennis Lee, Ignasi Clavera +2
Credit assignment in Meta-reinforcement learning (Meta-RL) is still poorly understood. Existing methods either neglect credit assignment to pre-adaptation behavior or implement it…
Model-Based Reinforcement Learning via Meta-Policy Optimization
Ignasi Clavera, Jonas Rothfuss, John Schulman +3
Model-based reinforcement learning approaches carry the promise of being data efficient. However, due to challenges in learning dynamics models that sufficiently match the real-wor…
Deep Episodic Memory: Encoding, Recalling, and Predicting Episodic Experiences for Robot Action Execution
Jonas Rothfuss, Fabio Ferreira, Eren Erdal Aksoy +2
We present a novel deep neural network architecture for representing robot experiences in an episodic-like memory which facilitates encoding, recalling, and predicting action exper…